Hida Mitsumasa, Eto Shinji, Wada Chikamune, Kitagawa Kodai, Imaoka Masakazu, Nakamura Misa, Imai Ryota, Kubo Takanari, Inoue Takao, Sakai Keiko, Orui Junya, Tazaki Fumie, Takeda Masatoshi, Hasegawa Ayuna, Yamasaka Kota, Nakao Hidetoshi
Department of Rehabilitation, Osaka Kawasaki Rehabilitation University, Mizuma 158, Kaizuka 597-0104, Japan.
Graduate School of Rehabilitation, Osaka Kawasaki Rehabilitation University, Mizuma 158, Kaizuka 597-0104, Japan.
Life (Basel). 2023 May 9;13(5):1146. doi: 10.3390/life13051146.
Hallux valgus, a frequently seen foot deformity, requires early detection to prevent it from becoming more severe. It is a medical economic problem, so a means of quickly distinguishing it would be helpful. We designed and investigated the accuracy of an early version of a tool for screening hallux valgus using machine learning. The tool would ascertain whether patients had hallux valgus by analyzing pictures of their feet. In this study, 507 images of feet were used for machine learning. Image preprocessing was conducted using the comparatively simple pattern A (rescaling, angle adjustment, and trimming) and slightly more complicated pattern B (same, plus vertical flip, binary formatting, and edge emphasis). This study used the VGG16 convolutional neural network. Pattern B machine learning was more accurate than pattern A. In our early model, Pattern A achieved 0.62 for accuracy, 0.56 for precision, 0.94 for recall, and 0.71 for F1 score. As for Pattern B, the scores were 0.79, 0.77, 0.96, and 0.86, respectively. Machine learning was sufficiently accurate to distinguish foot images between feet with hallux valgus and normal feet. With further refinement, this tool could be used for the easy screening of hallux valgus.
拇外翻是一种常见的足部畸形，需要早期发现以防止其恶化。这是一个医疗经济问题，因此一种快速识别它的方法会很有帮助。我们设计并研究了一种使用机器学习筛查拇外翻的早期工具的准确性。该工具将通过分析患者足部图片来确定患者是否患有拇外翻。在本研究中，507张足部图像用于机器学习。图像预处理使用相对简单的模式A（重新缩放、角度调整和裁剪）和稍复杂的模式B（相同操作，加上垂直翻转、二进制格式化和边缘增强）。本研究使用了VGG16卷积神经网络。模式B的机器学习比模式A更准确。在我们的早期模型中，模式A的准确率为0.62，精确率为0.56，召回率为0.94，F1分数为0.71。至于模式B，分数分别为0.79、0.77、0.96和0.86。机器学习在区分拇外翻足部和正常足部的图像方面足够准确。经过进一步完善，该工具可用于拇外翻的简易筛查。
